岸船通信环境存在高度非线性的多径效应和随机性极强的障碍物遮蔽效应，极大增加了对信号衰减的捕捉难度，影响路径损耗的预测精准性。故本研究结合分步傅里叶法，提出一种路径损耗智能预测方法。利用分步傅里叶法将非线性传播效应分解为线性与非线性组合，捕捉因多径效应引发的链路细微变化，精准计算收发端间的信号衰减值，并将障碍物遮蔽效应表征为主导衰减因子。采用蜣螂优化算法对衰减因子展开寻优，通过模拟蜣螂的滚球行为与觅食策略完成高效搜索，自动适应障碍物遮蔽效应的随机性。根据寻优结果智能预测路径损耗。实验表明，该方法可以精准预测路径损耗，相关系数始终保持在0.92以上，场景一致性变异系数未超过0.10，验证了该方法的准确性。
The communication environment between shore and ship has highly nonlinear multipath effects and highly random obstacle shielding effects, which greatly increase the difficulty of capturing signal attenuation and affect the accuracy of path loss prediction. Therefore, this study proposes an intelligent prediction method for path loss by combining the stepwise Fourier method. Using the stepwise Fourier method to decompose nonlinear propagation effects into linear and nonlinear combinations, capturing subtle changes in the link caused by multipath effects, accurately calculating the signal attenuation value between the transmitting and receiving ends, and characterizing the obstacle shielding effect as the dominant attenuation factor. Adopting the beetle optimization algorithm to optimize the attenuation factor, efficient search is achieved by simulating the beetle's rolling behavior and foraging strategy, automatically adapting to the randomness of obstacle shielding effects. Intelligent prediction of path loss based on optimization results. The experiment shows that this method can accurately predict path loss, with a correlation coefficient always above 0.92 and a scene consistency coefficient of variation not exceeding 0.10, verifying the accuracy of this method.
2026,48(3): 191-195 收稿日期：2025-9-30
DOI：10.3404/j.issn.1672-7649.2026.03.030
分类号：U675.75；TP391
作者简介：腾立国(1979-),男,硕士,讲师,研究方向为自动化与智能控制
参考文献：
[1] 刘文斌, 平洋, 王涛, 等. 船岸交互融合技术研究现状与未来展望[J]. 船舶工程, 2025, 47(2): 1-12.
LIU W B, PING Y, WANG T, et al. Research status and future prospects of ship-shore interaction fusion technology[J]. Ship Engineering, 2025, 47(2): 1-12.
[2] 李昭然, 金华标, 徐士甲. 船岸数据通信装置信号线电磁辐射分析[J]. 中国航海, 2023, 46(3): 105-110+125.
LI Z R, JIN H B, XU S J. Electromagnetic radiation analysis of signal lines in ship shore data communication devices[J]. Navigation of China, 2023, 46(3): 105-110+125.
[3] 余洪鑫, 冯菊, 欧阳琪翔, 等. 基于PE-PO混合方法的海洋大气波导环境下电大目标电磁散射研究[J]. 电波科学学报, 2025, 40(1): 29-36.
YU H X, FENG J, OUYANG Q X, et al. Study on electromagnetic scattering of electrically large targets in ocean atmosphere duct environment based on PE-PO hybrid method[J]. Chinese Journal of Radio Science, 2025, 40(1): 29-36.
[4] 陈冠旭, 刘经南, 刘焱雄, 等. 海洋通导一体化系统的发展与趋势[J]. 哈尔滨工程大学学报, 2023, 44(11): 1869-1882.
CHEN G X, LIU J N, LIU Y X, et al. Development and trends in marine integrated communication and navigation systems[J]. Journal of Harbin Engineering University, 2023, 44(11): 1869-1882.
[5] 孙铭然, 黄子蔚, 白露, 等. 基于感知图像信息的无人机信道路径损耗预测[J]. 模式识别与人工智能, 2023, 36(11): 987-996.
SUN M R, HUANG Z W, BAI L, et al. Sensing image data based unmanned aerial vehicle channel path loss prediction[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(11): 987-996.
[6] 廖希, 周萍, 周思洋, 等. 基于机器学习的城市环境跨频段跨场景路径损耗预测方法[J]. 重庆邮电大学学报(自然科学版), 2024, 36(6): 1099-1109.
LIAO X, ZHOU P, ZHOU S Y, et al. Cross-frequency band and cross-scenario path loss prediction method in urban environments based on machine learning[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition ), 2024, 36(6): 1099-1109.
[7] 赵玉超, 钱佳静, 芮义斌, 等. 基于CNN-GRU的对流层散射通信短期传输损耗预测[J]. 电讯技术, 2024, 64(8): 1175-1180.
ZHAO Y C, QIAN J J, RUI Y B, et al. Short-term transmission loss prediction of troposcatter communication based on CNN-GRU[J]. Telecommunication Engineering, 2024, 64(8): 1175-1180.
[8] MIRAY P G, Himmet K. Performance evaluation of geoai-based approach for path loss prediction in cellular communication Networks[J]. Wireless Personal Communications, 2024, 138(2): 1211-1246.
[9] 费敏学, 黄东岩, 郭晓新. 改进蜣螂算法优化机器学习模型[J]. 吉林大学学报(理学版), 2025, 63(4): 1117-1121.
FEI M X, HUANG D Y, GUO X X. Improve dung beetle algorithm to optimize machine learning model[J]. Journal of Jilin University (Science Edition), 2025, 63(4): 1117-1121.
[10] 潘劲成, 李少波, 周鹏, 等. 改进正弦算法引导的蜣螂优化算法[J]. 计算机工程与应用, 2023, 59(22): 92-110.
PAN J C, LI S B, ZHOU P, et al. Dung beetle optimization algorithm guided by improved sine algorithm[J]. Computer Engineering and Applications, 2023, 59(22): 92-110.
